© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 95127
    Prev
    Next
    INDEX
    Explanations

    there

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     there
    -2.22
    there
    -1.85
     There
    -1.61
    There
    -1.58
     THERE
    -1.41
    THERE
    -1.28
     هناك
    -1.17
     existem
    -0.87
     există
    -0.85
     ahí
    -0.82
    POSITIVE LOGITS
     thyself
    0.60
     thru
    0.60
     Itself
    0.60
     Jew
    0.59
    niająca
    0.59
    Amicalement
    0.59
    inose
    0.58
     Samaria
    0.57
     to
    0.57
     CURIAM
    0.57
    Activations Density 0.064%

    No Known Activations